Full-text search across 63233 articles. Combine with topic and date filters; results sorted by relevance.
A Cloudflare security-audit skill for AI coding agents surged to roughly +15.4k GitHub stars in seven days, according to a lead software engineer who examined the project. The skill turns agents such as Claude Code or Co…
JetBrains and the Rust Foundation will host the second episode of their AI Livestream series, "Smarter Coding Agents for Rust with Symposium," on October 1, 2026 at 16:00 UTC, hosted by Orhun Parmaksız, Rust Developer Ad…
A developer released Herobrine, an open-source Minecraft agent system that spawns real players via Mineflayer in vanilla worlds and drives every action through TypeSafe's JEV choice model, with a separate planner model (…
A developer outlines a workflow for using AI coding assistants the way a senior engineer would: define explicit behavior, ask the assistant to map existing authorization, membership and email flows before writing code, s…
Agent harnesses should treat plans as the runtime's authoritative state machine rather than a user-facing "Plan Mode" UI, according to an analysis of frontier coding assistants including Cursor, Windsurf, Claude Code, Ai…
The AI Native Dev community will host a meetup at Picnic HQ in Amsterdam on 23 September from 19:00 to 20:00 GMT+2, featuring a talk titled "Skills are the new Code" by Guy Podjarny, founder and CEO of Tessl and previous…
Claude Code does not enforce CLAUDE.md files because Anthropic's memory documentation states the content "is delivered as a user message after the system prompt, not as part of the system prompt itself," with no guarante…
DORA's 2025 State of AI-Assisted Software Development research found that roughly 80% of engineers using AI coding tools saw average productivity gains of only about 3%, while the top 20% of teams averaged gains near 55%…
Volt Active Data released free, MIT-licensed agent skills and a Model Content Protocol (MCP) server that let AI coding agents develop VoltDB applications and query a running VoltDB database. The initial skills, published…
A developer building the CourierIQ project used AI as a mentoring copilot rather than a code generator, prompting a tool called Antigravity to act as a senior developer that supplied steps and explanations while the deve…
Anthropic is rolling out a redesigned Claude Projects feature to selected Pro and Max subscribers using Claude Code cloud sessions, with existing web and desktop Projects users excluded from the initial phase. The coordi…
Harness Arena, an open-source platform for comparing AI agent harnesses, now lets signed-in users upload their own task datasets, select harnesses such as Codex, Claude Code, OpenCode and Hermes, choose a model, and subm…
Edouard Maleix argued in an AI Native DevCon talk that agent teams need a "knowledge factory" with attributed mistakes, provenance and measured corrections to stop paying repeatedly for the same failures, citing an agent…
A wave of malicious gems on RubyGems.org, traced by researchers including the registry's maintainer to OpenAI's bot infrastructure, embedded code that exploited a caching vulnerability in RubyGems.org and executed arbitr…
A developer's guide details how engineering teams are using AI tools to compress software development cycles, citing claims that AI now handles 42% of repetitive coding and testing tasks for top-performing teams and that…
Databricks released Omnigent, an Apache 2.0 open source meta harness, on 13 Jun 2026 under a post by Matei Zaharia, Kasey Uhlenhuth and Corey Zumar, with the latest release v0.13.0 published 9 Sep 2026. Omnigent runs Cla…
A developer measured how Claude Code loads a 2,004-word rule set from four different placements, finding that rules pasted inline, pulled in via @import, or stored unscoped in .claude/rules/ all added roughly 3,300–3,440…
Cognition's SWE-2 coding model scored 83.75% on the eight-task KingBench 3 benchmark, beating DeepSeek V4.1 Flash at 81.25% and its own base model Kimi K3 at 77.5%, according to independent testing. SWE-2 is post-trained…
GitHub announced on September 3 that four GitHub Copilot models — Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 — will be retired on October 2, giving developers 23 days to migrate to replacemen…
A developer explores whether developers will choose libraries based on what AI coding agents can write reliably, even if those libraries are harder for humans to learn. The post examines Effect and StyleX, which both wor…